© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26740
    Prev
    Next
    INDEX
    Explanations

    code elements or variable suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹īåĭĩ
    -0.06
    åĨ·æ¸ħ
    -0.06
    æ½¢
    -0.06
    lement
    -0.06
    xil
    -0.06
    âĢ³
    -0.06
    ä¹ĭåĪ«
    -0.06
    etti
    -0.06
    ä¹ĭ主
    -0.06
    ellini
    -0.06
    POSITIVE LOGITS
    евиÑĩ
    0.08
    apak
    0.08
    rait
    0.07
    ahead
    0.07
    jects
    0.07
     menda
    0.07
    wich
    0.07
    enticator
    0.07
    æł¼æĸ¯
    0.07
    éķ¿åĪ¶
    0.07
    Activations Density 0.342%

    No Known Activations